See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/356622131

Comparison of Classification Data Mining C4.5 and Naïve Bayes Algorithms of

EDM Dataset

Article  in  TEM Journal · November 2021

DOI: 10.18421/TEM104-34

CITATION READS

1 101

6 authors, including:

Muhammad Arifin Robbi Rahim

Universitas Muria Kudus Sekolah Tinggi Ilmu Manajemen Sukma, Medan, Indonesia
29 PUBLICATIONS   60 CITATIONS    326 PUBLICATIONS   4,495 CITATIONS   

SEE PROFILE SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Housing Urban Poor and Urban Revitalisation. KLN Grant Ministry of Research, Technology and Higher Education Republic of Indonesia View project

Sistem Keamanan Pintu Berbasis Arduino Mega View project

All content following this page was uploaded by Muhammad Arifin on 10 July 2022.

The user has requested enhancement of the downloaded file.

 TEM Journal. Volume 10, Issue 4, Pages 1738-1744, ISSN 2217-8309, DOI: 10.18421/TEM104-34, November 2021. 

Comparison of Classification Data Mining C4.5

and Naïve Bayes Algorithms of EDM Dataset
Joseph Teguh Santoso 1, Ni Luh Wiwik Sri Rahayu Ginantra 2, Muhammad Arifin 3,
R Riinawati 4, Dadang Sudrajat 5, Robbi Rahim 6
1
Universitas STEKOM, Semarang, Indonesia
2
STMIK STIKOM Indonesia, Denpasar, Indonesia
3
Universitas Muria Kudus, Kudus, Indonesia
4
Universitas Islam Negeri Antasari, Banjarmasin, Indonesia
5
STMIK IKMI Cirebon, Cirebon, Indonesia
6
Sekolah Tinggi Ilmu Manajemen Sukma, Medan, Indonesia

Abstract - The purpose of this research is to choose 1. Introduction

the best method by comparing two classification
methods of data mining C4.5 and Naïve Bayes on Making comparisons with several data mining
Educational Data Mining, in which the data used is classification methods to find out the best results is
student graduation data consisting of 79 records. Both
one way to get the best classification and prediction
methods are tested for validation with 10-ford X
Validation and perform a T-Test difference test to results [1], [2], [3], [4]. Some of the most widely
produce a table that contains the best method ranking. used classification methods in classifying and
Different results were obtained for each method. Based predicting are the Decision Tree method (C4.5),
on the results of these two methods, it is very Naive Bayes and KNN [5], [6], [7]. There is related
influential on the dataset and the value of the area research that has been done in determining the best
under curve in the Naïve Bayes method is better than classification method with various existing problems.
the C4.5 method in various datasets. Comparison of The results obtained are also different for each
the method with the 10-Ford X Validation test and the problem [8]. Research [9] is done on the prediction
T-Test difference test is that the Naïve Bayes method is of lung cancer survival. This paper proposes two
better than C4.5 with an average accuracy value of
classification techniques, namely the C4.5 algorithm
73.41% and an under-curve area of 0.664.
and the Naive Bayes algorithm. The aim of the
Keywords: Comparison, data mining, Classification, project is to verify the effectiveness of the
C4.5, Naive Bayes, Performance, EDM. predictions of the two techniques on actual historical
data. The results show that the C4.5 algorithm is
slightly better than Naive Bayes.
Furthermore, research by [10] on evaluating the
DOI: 10.18421/TEM104-34 
classification accuracy of the C4.5 and Naïve Bayes
https://doi.org/10.18421/TEM104-34 
methods using the Ljubljana Breast Cancer dataset.
Corresponding author: Robbi Rahim,  The paper proposes an evaluation of the accuracy of
Sekolah  Tinggi  Ilmu  Manajemen  Sukma,  Medan,  two classification methods (C4.5 and Naive Bayes).
Indonesia.  The results of the classification methods C4.5 and
Email: usurobbi85@zoho.com  Naïve Bayes in terms of accuracy for various cross-
Received:   04 July 2021.  validation folds show the same accuracy results in
Revised:     26 October 2021.  the Ljubljana Breast Cancer dataset.
Accepted:   30 October 2021.  Furthermore, research by Suseno [11] on the
Published:  26 November 2021.  classification of people who receive zakat
(mustahik). This paper proposes a comparison of the
©  2021  Joseph  Teguh  Santoso  et  al; 
two classification methods in the case of people
published  by  UIKTEN.  This  work  is  licensed  under  the 
receiving zakat. By using split validation, the results
Creative  Commons  Attribution‐NonCommercial‐NoDerivs 
of the study concluded that the use of the C4.5
4.0 License.
method was better than the Naive Bayes method.
The  article  is  published  with  Open  Access  at  This is evidenced by the level of accuracy ranging
www.temjournal.com  from 75% - 100% and execution time of 0 seconds.

1738     TEM Journal – Volume 10 / Number 4 / 2021. 
 TEM Journal. Volume 10, Issue 4, Pages 1738‐1744, ISSN 2217‐8309, DOI: 10.18421/TEM104‐34, November 2021. 

Further research by Pujianto [12] on Diabetes
Patients with HbA1c Measurement. This paper
proposes two comparisons of classification methods
C4.5 and Naive Bayes with HbA1c measurement in
seeing the performance of the two methods. By
involving a combination of preprocessing methods,
namely Synthetic Minority Over-Sampling
Technique (SMOTE) and the Wrapper feature
selection method, with both classification techniques.
The result of the research states that the C4.5 method
produces the best performance in classifying diabetic
patients with an accuracy value of 82.74%, a
precision value of 87.1%, and a recall value of
82.7%.
Based on related research, the results obtained
from the best classification method differ according
to the cases used. The purpose of this study was to
evaluate the performance of the C4.5 and Naïve
Bayes classification methods by performing a
validation test with 10-Ford X Validation and
performing a T-Test differential test [13]. The case
raised is Educational Data Mining (EDM) [14] on the
student graduation dataset in the research conducted
[15], [16]. By changing the dataset as training and
testing data, it is hoped that it can evaluate the
selection of the best classification method.
2. Methodology
2.1. Dataset
The dataset used is the graduation data of students
majoring in informatics engineering at University
XYZ which consists of 79 data from students who
have graduated from various generations. The
attributes used are regional origin, type of school,
entrance, predicate cumulative graduation (IPK),
predicate of graduation in the first semester (IP1),
predicate of second semester graduation (IP2),
predicate of third semester graduation (IP3),
predicate of fourth semester graduation (IP4),
predicate of fifth semester graduation (IP5), boarding
school and information. The following is the student
graduation dataset as shown in Table 1 below:

Table 1. Research data

Boarding
Origin School Entrance IPK IP1 IP2 IP3 IP4 IP5 Information
school
East Java MAN 1 C B B B B B No Incorrect
East Java MAS 2 B C C B B C No Incorrect
East Java SMAN 1 B B B C C B No Incorrect
Madura SMAN 2 B A B B B B No Incorrect
East Java MAN 1 B C B C B B Yes Incorrect
West Java SMKS 2 B B B B B B No Incorrect
East Java MAS 1 B C B C B B Yes Incorrect
East Java MAN 1 B C B C C B No Incorrect
East Java MAS 1 B B C B B C Yes Incorrect
East Java MAS 1 B B B B B B Yes Incorrect
East Java MAN 4 B B B B B B No Incorrect
East Java SMAN 3 B B B B B B Yes Incorrect
East Java SMAN 1 B B B B B B No Incorrect
East Java SMAN 1 C B C B B C No Incorrect
East Java SMAN 1 B B C B B B No Incorrect
Sumatra MAN 1 B B B C B C Yes Incorrect
Sumatra MAS 1 B C C B B B Yes Incorrect
East Java SMAN 1 B B B C C B No Incorrect
East Java SMAN 1 B B C B B C No Incorrect
Sumatra SMAN 1 B B B C C B No Incorrect
… … … … … … … … … … …
… … … … … … … … … … …
East Java SMAN 1 B B C C B B Yes Incorrect
East Java SMAS 3 B B B B B A No Incorrect
Madura SMAS 1 B C C B B B Yes Incorrect
source: [15]
In Table 1 it can be explained that the dataset will graduation using numbers and letters based on the
be used to compare the best classification method by research dataset.
performing a validation test with 10-Ford X
Validation and performing a T-Test difference test. Table 2. Predicate of Graduation
Training and testing data is divided into three Achievement Letter
datasets, namely dataset 1 (25 records), dataset 2 (50 No
Index Value Value
Predicate
records) and dataset 3 (79 records). The analysis
process was carried out using the Rapid Miner 1 3,51 – 4,00 A With Praise (Cumlaude)
software. The following is an explanation of the 2 3,00 – 3,50 B Very satisfy
attributes of the type of school and the predicate of 3 2,51 – 2,99 C Satisfactory
4 2,00 – 2,50 D Enough

TEM Journal – Volume 10 / Number  4 / 2021.                                                                                                                     1739 
 TEM Journal. Volume 10, Issue 4, Pages 1738‐1744, ISSN 2217‐8309, DOI: 10.18421/TEM104‐34, November 2021.
Table 3. Entrance
No Entrance
1 Mandiri Ujian Tulis
2 SNMPTN Ujian Tulis
3 Mandiri Prestasi
4 SNMPTN Undangan
5 SPMB - PTAIN
2.2. Classification Algorithms
The proposed classification algorithm aims to
achieve a balance between the classification methods
used by comparing the performance of these models
[6]. The methods used are the decision tree (C4.5)
and the traditional statistical classifier (Naïve Bayes)
[17].
2.3. Model Validation
The validation model [18] used is cross validation
10-fold stratified, which means dividing the training
3. Results and Discussion
This stage of the analysis process uses the
assistance of Rapid Miner software in comparing the
best classification method on the student graduation
dataset which is divided into three datasets. The
following is a design model for the comparison of the
C4.5 method with Naïve Bayes using the Rapid
Miner software as in Figure 1 below:
(a)
(b)
(c)
Figure 1. Classification Method Comparison Design
Model (a)(b)(c)
1740                                                                                                                   TEM Journal – Volume 10 / Number 4 / 2021.
 
dataset into 10 equal parts and then do the learning
process 10 times and use the rest of the dataset to
Score perform the test. Several tests mention the use of this
1 validation model stratification slightly increased
2 yield [11].
3
4
5 2.4. Model Evaluation
Apply the area under the curve (AUC) for accuracy
indicator is to increase increasing convergence across
experiments. The following is guidance Table for
classifying accuracy using AUC as shown in Table 4
[6].
Table 4. AUC value
AUC Meaning
0.90 - 1.00 Excellent Classification
0.80 - 0.90 Good Classification
0.70 - 0.80 Fair Classification
0.60 - 0.70 Poor Classification
< 0.60 Failure
In Figure 1 (a), the input dataset uses three different
datasets (25, 50 and 79) with excel format (.xls). The
design uses the multiply operator which functions as
a bridge in comparing to the classification methods
used at once (C4.5 and Naïve Bayes). After that each
method uses the Cross Validation operator which
uses the 10-Ford X Validation test on training and
testing data (b) (c). Then the further determination is
used testing using statistical tests, namely by using
the T-Test to compare two methods alternately.
Following are the results of a comparative analysis of
the C4.5 and Naïve Bayes methods for various
datasets (25, 50 and 79).
3.1. Results of Comparative Analysis of Methods
with Dataset 3 (79 records)
a) C4.5 (Decision tree)
The following are the results of the analysis of the
C4.5 method using RapidMiner software for
validation tests with 10-Ford X Validation and T-
Test differences as shown in Figures 2 and 3 below:
Figure 2. C4.5 accuracy results (79 records)
 
 TEM Journal. Volume 10, Issue 4, Pages 1738‐1744, ISSN 2217‐8309, DOI: 10.18421/TEM104‐34, November 2021. 

In Figure 2, it is explained that the accuracy value

obtained is 87.32%. Here is the AUC value for
measuring discriminatory performance with estimate
the probability of output from the sample randomly
selected from a positive or negative population. Figure 6. T-Test Statistics Test (79 record)

From the t-test above, that results comparison

between C4.5 and Naive Bayes methods there is no
significant difference (H0).

Table 5. Comparison results of all tests (79 records)

Dataset C4.5 Naïve Bayes
AUC
Accuracy AUC value Accuracy
value
79 87.32% 0.664 83.57% 0.786

Based on the Table above, it can be seen that the

Figure 3. Result of AUC (Area Under the ROC Curve) at
C4.5 (79 records)
In Figure 3, the best AUC value is 0.664 and is
included in the category of "Poor Classification".
C4.5 algorithm has an accuracy value the highest was
87.32% and Naïve Bayes 83.57%. Meanwhile, the
ROC curve (AUC) test shows that Naïve Bayes
achieved the best AUC value of 0.786 compared to
C4.5, which is 0.664.

b) Naive Bayes 3.2. Results of Comparative Analysis of Methods

with Dataset 2 (50 records)
The following are the results of the analysis of the
Naïve Bayes method using RapidMiner software for
a) C4.5 (Decision tree)
validation tests with 10-Ford X Validation and T-
Test differences as shown in Figures 4 and 5 below: The following are the results of the analysis of the
C4.5 method using RapidMiner software for
validation tests with 10-Ford X Validation and T-
Test differences as shown in Figures 7 and 8 below:

Figure 4. Naïve Bayes accuracy results (79 records)

In Figure 4, it is explained that the accuracy value

obtained is 83.57%. Here is the AUC value for
measuring discriminatory performance with estimate Figure 7. C4.5 accuracy results (50 records)
the probability of output from the sample randomly
selected from a positive or negative population. In Figure 7, it is explained that the accuracy value
obtained is 76%. Here is the AUC value for
measuring discriminatory performance with estimate
the probability of output from the sample randomly
selected from a positive or negative population.

Figure 5. Result of AUC (Area Under the ROC Curve) at

Naïve Bayes (79 records)

In Figure 5, the best AUC value is 0.786 and is

included in the category of "Fair Classification". Figure 8. Result of AUC (Area Under the ROC Curve) at
C4.5 (50 records)

TEM Journal – Volume 10 / Number  4 / 2021.                                                                                                                     1741 
 TEM Journal. Volume 10, Issue 4, Pages 1738‐1744, ISSN 2217‐8309, DOI: 10.18421/TEM104‐34, November 2021.
In Figure 3, the best AUC value is 0.350 and is
included in the category of "Failure ".
b) Naive Bayes
The following are the results of the analysis of the
Naïve Bayes method using RapidMiner software for
validation tests with 10-Ford X Validation and T-
Test differences as shown in Figures 9 and 10 below:
Figure 9. Naïve Bayes accuracy results (50 records)
In Figure 4, it is explained that the accuracy value
obtained is 80%. Here is the AUC value for
measuring discriminatory performance with estimate
the probability of output from the sample randomly
selected from a positive or negative population.
Figure 10. Result of AUC (Area Under the ROC Curve) at
Naïve Bayes (50 records)
In Figure 10, the best AUC value is 0.750 and is
included in the category of "Fair Classification".
Figure 11. T-Test Statistics Test (50 record)
From the t-test above, that results comparison
between C4.5 and Naive Bayes methods there is no
significant difference (H0).
Table 6. Comparison results of all tests (50 records)
Dataset C4.5 Naïve Bayes
AUC
Accuracy AUC value Accuracy
value
50 76% 0.35 80% 0.75
1742                                                                                                                   TEM Journal – Volume 10 / Number 4 / 2021.
 
Based on the Table above, it can be seen that the
Naive Bayes algorithm has an accuracy value the
highest is 80% and C4.5 is 76%. Meanwhile, the
ROC curve (AUC) test shows that Naïve Bayes
achieved the best AUC value, namely 0.75.
Meanwhile, Method C4.5 is in the Failed category
because it is <0.60.
3.3. Results of Comparative Analysis of Methods
with Dataset 1 (25 records)
a) C4.5 (Decision tree)
The following are the results of the analysis of the
C4.5 method using RapidMiner software for
validation tests with 10-Ford X Validation and T-
Test differences as shown in Figures 12 and 13
below:
Figure 12. C4.5 accuracy results (25 records)
In Figure 12, it is explained that the accuracy value
obtained is 46.67%. Here is the AUC value for
measuring discriminatory performance with estimate
the probability of output from the sample randomly
selected from a positive or negative population.
Figure 13. Result of AUC (Area Under the ROC Curve) at
C4.5 (25 records)
In Figure 13, the best AUC value is 0.425 and is
included in the category of "Failure ".
b) Naive Bayes
The following are the results of the analysis of the
Naïve Bayes method using RapidMiner software for
validation tests with 10-Ford X Validation and T-
Test differences as shown in Figures 14 and 15
below:
 
 TEM Journal. Volume 10, Issue 4, Pages 1738‐1744, ISSN 2217‐8309, DOI: 10.18421/TEM104‐34, November 2021. 

are used to carry out research using the Rapid Miner

software. In Table 8, you can see the accuracy and
AUC values of each method based on the AUC
evaluation model.
Table 8. Comparison results of all tests
Figure 14. Naïve Bayes accuracy results (25 records)
Naïve
Naïve
C4.5 C4.5
In Figure 14, it is explained that the accuracy value Bayes
Bayes
obtained is 56%. Here is the AUC value for AUC
Dataset Accuracy Accuracy AUC value
measuring discriminatory performance with estimate value
the probability of output from the sample randomly 79 87.32% 83.57% 0.664 0.786
selected from a positive or negative population. 50 76% 80% 0.35 0.75
25 46.67% 56.67% 0.425 0.7
Average 70.00% 73.41% 0.48 0.75

Based on Table 8, it can be concluded that in the

Figure 15. Result of AUC (Area Under the ROC Curve) at
Naïve Bayes (25 records)
In Figure 10, the best AUC value is 0.7 and is
included in the category of "Fair Classification".
T-Test, the C4.5 and Naïve Bayes methods showed
non-dominant results. Based on the three datasets
used, the Naïve Bayes method shows better results
than the C4.5 method. In 3 experiments (3 datasets),
all methods showed a decrease in accuracy for each
data test. In the C4.5 method, the highest accuracy is
87.32% on the 79 record dataset. While the Naïve
Bayes method, the highest accuracy is 83.57% and
80% on the 79 and 50 datasets. Meanwhile, the AUC
value that achieves the maximum results is the Naïve
Bayes method with values of 0.789, 0.75 and 0.7.
While the AUC value that reaches the maximum
result is 0.664. Based on these results, the Naïve
Bayes Method is the best classification method on
the EDM dataset with an average accuracy value of
73.41% and an area of under curve (AUC) of 0.664.
The following is a comparison chart of the
classification method based on the accuracy and
AUC values for each dataset.

Figure 16. T-Test Statistics Test (25 record)

From the t-test above, that results comparison
between C4.5 and Naive Bayes methods there is no
significant difference (H0).
Table 7. Comparison results of all tests (25 records)
Dataset C4.5 Naïve Bayes
AUC (a)
Accuracy AUC value Accuracy
value
25 46.67% 0.425 56.67% 0.7
Based on the Table above, it can be seen that the
Naive Bayes algorithm has an accuracy value the
highest is 56.67% and C4.5 is 46.67%. Meanwhile,
the ROC curve (AUC) test shows that Naïve Bayes
achieved the best AUC value, namely 0.7.
Meanwhile, Method C4.5 is in the Failed category
because it is <0.60.

3.4. Discussion
Experiments were carried out on a laptop based on (b)
an Intel Core i5, Processor with 8 GB RAM and an Figure 17. The results of the comparison graph of all tests
operating system Windows 8 is used. Applications (a)(b)

TEM Journal – Volume 10 / Number  4 / 2021.                                                                                                                     1743 
 TEM Journal. Volume 10, Issue 4, Pages 1738‐1744, ISSN 2217‐8309, DOI: 10.18421/TEM104‐34, November 2021.
4. Conclusion
Based on the comparison of data mining
classification algorithms, namely C.45 and Naïve
Bayes, for the graduation dataset of informatics
engineering students at University XYZ which
consists of 79 records that have passed from various
generations can be done. The results of accuracy and
AUC are very influential on the dataset used. The
larger the dataset used, the better the accuracy value
results. Evidenced by a small dataset, the accuracy
value for both methods is greatly reduced.
Meanwhile for AUC, the Naïve Bayes method is
better than the C.45 method.
References
[1]. Afiyah, A. N., Dengen, N., & Taruk, M. (2019,
October). Comparison Performance of C4. 5, Naïve
Bayes and K-Nearest Neighbor in Determination
Drug Rehabilitation. In 2019 5th International
Conference on Science in Information Technology
(ICSITech) (pp. 112-117). IEEE.
[2]. Hssina, B., Merbouha, A., Ezzikouri, H., & Erritali,
M. (2014). A comparative study of decision tree ID3
and C4. 5. International Journal of Advanced
Computer Science and Applications, 4(2), 13-19.
Doi: 10.14569/SpecialIssue.2014.040203.
[3]. Arumugam, P., & Christy, V. (2018). Analysis of
clustering and classification methods for actionable
knowledge. Materials Today: Proceedings, 5(1),
1839-1845. Doi: 10.1016/j.matpr.2017.11.283
[4]. Efendi, Y., Imardi, S., Muzawi, R., Syaifullah, M.,
2021. Application of RFID internet of things for
school empowerment towards smart school. Jurnal
Pengabdian Dan Pemberdayaan Masyarakat Indonesia
1(2): 48–58.
[5]. Suyadi, S., Setyanto, A., & Al Fattah, H. (2017).
Analisis perbandingan algoritma Decision tree (C4. 5)
dan K-naïve bayes untuk mengklasifikasi penerimaan
mahasiswa baru tingkat universitas. Indonesian
Journal of Applied Informatics, 2(1), 59-68.
Doi: 10.20961/ijai.v2i1.13258.
[6]. Wahono, R. S., Herman, N. S., & Ahmad, S. (2014).
A comparison framework of classification models for
software defect prediction. Advanced Science
Letters, 20(10-11), 1945-1950.
Doi: 10.1166/asl.2014.5640
[7]. Yousefi, M., Hooshyar, D., Remezani, A., Sahari, K.
S. M., Khaksar, W., & Alnaimi, F. B. I. (2015). Short-
term wind speed forecasting by an adaptive network-
based fuzzy inference system (ANFIS): an attempt
towards an ensemble forecasting
method. International Journal of Advances in
Intelligent Informatics, 1(3), 140-149.
Doi: 10.26555/ijain.v1i3.45.
1744                                                                                                                   TEM Journal – Volume 10 / Number 4 / 2021.
View publication stats
 
[8]. Conejero, J. M., Preciado, J. C., Fernández-García, A.
J., Prieto, A. E., & Rodríguez-Echeverría, R. (2021).
Towards the use of Data Engineering, Advanced
Visualization techniques and Association Rules to
support knowledge discovery for public
policies. Expert Systems with Applications, 170,
114509. Doi: 10.1016/j.eswa.2020.114509.
[9]. Dimitoglou, G., Adams, J. A., & Jim, C. M. (2012).
Comparison of the C4. 5 and a Naïve Bayes classifier
for the prediction of lung cancer survivability. arXiv
preprint arXiv:1206.1121.
[10]. Sivakumari, S., Praveena Priyadarsini, R., &
Amudha, P. (2009). Accuracy evaluation of C4. 5 and
Naive Bayes classifiers using attribute ranking
method. International journal of computational
intelligence systems, 2(1), 60-68.
[11]. H. Suseno, A. Wanhari, and S. Masruroh,
“Comparison of C4.5 and Naïve Bayes Algorithm for
Mustahik Classification,” Proc. 2nd Int. Colloq.
Interdiscip. Islam. Stud. Conjunction with 3rd Int.
Conf. Quran Hadith Stud., 2020, doi: 10.4108/eai.7-
11-2019.2294560.
[12]. Pujianto, U., Setiawan, A. L., Rosyid, H. A., &
Salah, A. M. M. (2019). Comparison of naïve bayes
algorithm and decision tree C4. 5 for hospital
readmission diabetes patients using hba1c
measurement. Knowledge Engineering and Data
Science, 2(2), 58-71.
Doi: 10.17977/um018v2i22019p58-71.
[13]. Triyanto, Y., Sepriani, Y., Mustamu, N. E., Siregar,
R. A., & Rambe, B. H. (2021, June). Implementation
of PROMETHEE Method for Potential Suitability of
Land Oil Palm Plant. In Journal of Physics:
Conference Series (Vol. 1933, No. 1, p. 012060). IOP
Publishing.
[14]. Shin, D., & Shim, J. (2021). A Systematic Review
on Data Mining for Mathematics and Science
Education. International Journal of Science &
Mathematics Education, 19(4).
Doi: 10.1007/s10763-020-10085-7.
[15]. Mashlahah, S. (2013). Prediksi kelulusan mahasiswa
menggunakan metode decision tree dengan
penerapan algoritma C4. 5 (Doctoral dissertation,
Universitas Islam Negeri Maulana Malik Ibrahim).
[16]. Suryani, L., Lestari, B., Al_barazanchi, I., Ahmad, I.,
& Singh, M. K. S. (2021). Al-qur'an education park at
el-hasan terban mosque, gondokusuman, yogyakarta
city. Jurnal Pengabdian dan Pemberdayaan
Masyarakat Indonesia, 1(1), 1.
[17]. Xing, W., Li, C., Chen, G., Huang, X., Chao, J.,
Massicotte, J., & Xie, C. (2020). Automatic
Assessment of Students’ Engineering Design
Performance Using a Bayesian Network
Model. Journal of Educational Computing Research.
Doi: 10.1177/0735633120960422.
[18]. Susanto, E., Novitasari, Y., Rahman, W., & Amane,
A. P. O. (2019, December). Designing Software to
Introduce the Musical Instruments. In Journal of
Physics: Conference Series (Vol. 1364, No. 1, p.
012031). IOP Publishing.